About the tsurime tag
tsurime is a face part tag that NovelAI Diffusion can use. On Danbooru it has 40,824 posts, and its best-rated still image scores 1,635. The samples above put the tag at the front of a fixed base prompt with seed 1234, so the differences between tags come from the tag alone.
How each model draws tsurime
Follows composition and expression instructions closely, so the effect shows in a tidy form.
Reacts to the tag more strongly, so its effect is easier to see.
WAI illustrious SDXL v17, a local model. Shows how the same tag reads outside NovelAI.
Writing tsurime in a prompt
Put the subject first, then this tag, then quality tags.
1girl, solo, tsurime, best quality, masterpiecewlop, 1girl, tsurimeThe negative prompt and the full settings are on the terms page.
How these samples were made
Every image uses 832×1216, seed 1234, 23 steps and the k_euler_ancestral sampler. The base prompt and negative prompt stay the same for every tag, and only the tag under test changes. Images flagged by the NSFW check are regenerated with a new seed or hidden.
From the Danbooru wiki
Show the wiki text ▾Hide ▴
Eyes drawn with the top eyelid slanting inwards. This usually produces a strong, piercing look and is generally given to characters with forceful personalities (naturally, exceptions exist). Also known as a positive canthal tilt or slanted eyes.
Opposite is tareme, which usually produces a gentle, weak look.
Examples
- : Kagami of Lucky Star
- : Kashima of Kantai Collection
- : Above - Tsurime, Below - Normal tilted eyes
Related tags
- jitome - eyes topped with a flat line
- sanpaku - eyes that show white primarily above or below the iris
- tareme - eyes with a rounded, downturned shape
- tsurime - eyes with an upward outer "point"
- v-shaped eyes
- v-shaped eyebrows
See also
FAQ
Does NovelAI recognize tsurime?
Compare the samples on this page. Every tag on this site shares the same seed and base prompt, so any change you see comes from tsurime.
How do I write tsurime in a prompt?
Write "tsurime" near the front of the prompt and separate it from other tags with commas.
Should I use V5 or V4.5?
V4.5 shows the tag's effect more strongly. V5 gives steadier images with fewer artifacts.